Welcome to cuML’s documentation!

cuML is a suite of fast, GPU-accelerated machine learning algorithms designed for data science and analytical tasks. Our API mirrors Sklearn’s, and we provide practitioners with the easy fit-predict-transform paradigm without ever having to program on a GPU.

As data gets larger, algorithms running on a CPU becomes slow and cumbersome. RAPIDS provides users a streamlined approach where data is initially loaded in the GPU, and compute tasks can be performed on it directly.

cuML is fully open source, and the RAPIDS team welcomes new and seasoned contributors, users and hobbyists! Thank you for your wonderful support!

An installation requirement for cuML is that your system must be Linux-like. Support for Windows is possible in the near future.

Contents:

• Introduction
  • 1. Where possible, match the scikit-learn API
  • 2. Accept flexible input types, return predictable output types
  • 3. Be fast!
  • Learn more
• API Reference
  • Module Configuration
  • Preprocessing, Metrics, and Utilities
  • Regression and Classification
  • Clustering
  • Dimensionality Reduction and Manifold Learning
  • Neighbors
  • Time Series
  • Model Explainability
  • Multi-Node, Multi-GPU Algorithms
  • Experimental
• User Guide
  • Training and Evaluating Machine Learning Models
  • Pickling Models for Persistence
  • cuML on GPU and CPU
• Blogs and other references
  • Integrations, applications, and general concepts
  • Tree and forest models
  • Other popular models
  • Academic Papers

Indices and tables

• Index

• Module Index

• Search Page